ToolUniverse is a collection of tools, interfaces, and supporting components for building AI systems that perform scientific work. It is for developers creating AI scientist agents that use APIs, databases, machine-learning tools, and domain-specific utilities. The catalogue includes skills, commands, an MCP server, an agent, and a hook for working with the ecosystem.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add mims-harvard/ToolUniverse --skill tooluniverse-clinical-trial-protocolgit clone --depth 1 https://github.com/mims-harvard/ToolUniverseWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-clinical-trial-protocol)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-clinical-trial-protocol"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-clinical-trial-protocol/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-clinical-trial-protocol"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-clinical-trial-protocol.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00146 | $0.01853 |
| Opus 5.5 | $0.00058 | $0.00741 |
| Sonnet 5.5 | $0.00029 | $0.00371 |
| Haiku 4.5 | $0.00015 | $0.00185 |
Grade A, and why
tooluniverse-clinical-trial-protocol scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clinical Trial Protocol Generation
Turns a trial concept into an actual protocol DOCUMENT, grounded in real precedent-trial and regulatory-database lookups plus a genuine statistical sample-size calculation.
This skill is a downstream step, not a replacement for tooluniverse-clinical-trial-design. That skill answers "is this trial feasible, and what should endpoint/population/comparator/effect-size/duration/regulatory-pathway be?" (a 0-100 feasibility score with evidence grading). This skill takes those six answers — freshly run or already available from a prior tooluniverse-clinical-trial-design report — and drafts the actual protocol sections around them. Do not re-derive feasibility scoring, endpoint selection reasoning, or regulatory-pathway strategy here — call tooluniverse-clinical-trial-design for that and consume its output.
When to Use This Skill
- "Write me a clinical trial protocol for [drug/device]"
- "Generate an FDA submission protocol for our Phase 2 study"
- "Draft the statistical analysis plan / sample size section"
- "I have the feasibility assessment — now turn it into a protocol document"
- "What sample size do I need for a [proportion/continuous/survival] endpoint?"
NOT for (use other skills instead)
- Feasibility scoring, endpoint/population/comparator selection strategy ->
tooluniverse-clinical-trial-design(run this FIRST if not already done) - Patient-to-trial matching for an individual patient ->
tooluniverse-clinical-trial-matching - Drug mechanism / preclinical investigation ->
tooluniverse-drug-researchortooluniverse-drug-mechanism-research - Jurisdiction-aware approval/exclusivity lookups outside the protocol context ->
tooluniverse-drug-regulatory
Workflow
Step 1 — Confirm feasibility inputs exist
Ask the user (or check the conversation) whether a tooluniverse-clinical-trial-design feasibility report already exists for this indication/intervention.
- If yes: reuse its 6-dimension findings directly (endpoint, population, comparator, effect size, duration, regulatory pathway, plus the evidence grades A-D).
- If no: run
tooluniverse-clinical-trial-designfirst. Do not guess these six answers yourself — that skill's precedent-based reasoning exists precisely so this step doesn't fabricate them.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 99 lines · 146 tokens per session scan A b8c5c6e8217a
tooluniverse-clinical-trial-protocol is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,744 stars, last pushed yesterday), licensed Apache-2.0. It adds 146 tokens to every session and 1,853 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-07.
Other skills, from other repositories
ai-agent-tool-routing
Use when designing or reviewing an AI agent tool registry or MCP router: document parameter schemas, caller authorization, execution limits, replay-safe retries and verification evidence.
nanoresearch-writing
Draft a LaTeX research paper from all previous stage outputs.
construct-toy-examples
Generate and analyze simpler examples that satisfy both the assumptions and the conclusion of a theorem statement or subgoal. Use when you are stuck in reasoning and need simpler examples to regain traction, or when you want to see where the assumptions take effect and gain intuition.
obtain-immediate-conclusions
Derive immediate mathematical consequences from a theorem statement or subgoal. Use when starting a new problem, branch, or subgoal, or when cheap progress or a cleaner reformulation is needed before deeper proof search.
clinical-research-analysis-framework
Guided workflow for statistical and ML analysis of clinical data. Use when planning or executing research analyses on MIMIC, eICU, or similar EHR data. Ensures methodological rigor through structured consultation, assumption checking, and stepwise execution with audit trails.
apache-iv-score
Calculate APACHE IV (Acute Physiology and Chronic Health Evaluation IV) score for ICU mortality prediction. Use for severity assessment, hospital mortality prediction, ICU benchmarking, or case-mix adjustment. eICU has pre-computed scores; MIMIC-IV requires custom implementation with diagnosis mapping challenges.